On the Effect of Image Resolution on Semantic Segmentation

2024-02-08 · Ritambhara Singh, Abhishek Jain, Pietro Perona, Shivani Agarwal, Junfeng Yang

High-resolution semantic segmentation requires substantial computational resources. Traditional approaches in the field typically downscale the input images before processing and then upscale the low-resolution outputs back to their original dimensions. While this strategy effectively identifies broad regions, it often misses finer details. In this study, we demonstrate that a streamlined model capable of directly producing high-resolution segmentations can match the performance of more complex systems that generate lower-resolution results. By simplifying the network architecture, we enable the processing of images at their native resolution. Our approach leverages a bottom-up information propagation technique across various scales, which we have empirically shown to enhance segmentation accuracy. We have rigorously tested our method using leading-edge semantic segmentation datasets. Specifically, for the Cityscapes dataset, we further boost accuracy by applying the Noisy Student Training technique.

📄 PDF Abstract BibTeX arXiv:2402.05398

Code (0)

등록된 구현이 없습니다.

Tasks

Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

RandAugment 설명 없음

Stochastic Depth Stochastic Depth aims to shrink the depth of a network during training, while keeping it unchanged during testing. This is achieved by randomly dropping entire…

Noisy Student 설명 없음

Semantic Segmentation Using Super Resolution Technique as Pre-Processing

2023-06-27 · Chih-Chia Chen, Wei-Han Chen, Jen-Shiun Chiang, Chun-Tse Chien 외

Combining high-level and low-level visual tasks is a common technique in the field of computer vision. This work integrates the technique of image super resolution to semantic segmentation for document image binarization…

Binarization Image Super-Resolution Segmentation Semantic Segmentation+1

Semantic Segmentation Prior for Diffusion-Based Real-World Super-Resolution

2024-12-04 · Jiahua Xiao, Jiawei Zhang, Dongqing Zou, Xiaodan Zhang 외

Real-world image super-resolution (Real-ISR) has achieved a remarkable leap by leveraging large-scale text-to-image models, enabling realistic image restoration from given recognition textual prompts. However, these meth…

Image Restoration Image Super-Resolution Segmentation Semantic Segmentation+1

Label Refinement Network for Coarse-to-Fine Semantic Segmentation

2017-03-01 · Md Amirul Islam, Shujon Naha, Mrigank Rochan, Neil Bruce 외

We consider the problem of semantic image segmentation using deep convolutional neural networks. We propose a novel network architecture called the label refinement network that predicts segmentation labels in a coarse-t…

Image Segmentation Segmentation Semantic Segmentation

Dual Super-Resolution Learning for Semantic Segmentation

2020-06-01 · CVPR 2020 6 · Li Wang, Dong Li, Yousong Zhu, Lu Tian 외

Current state-of-the-art semantic segmentation methods often apply high-resolution input to attain high performance, which brings large computation budgets and limits their applications on resource-constrained devices. I…

Crack Segmentation Image Super-Resolution Pose Estimation Segmentation+2

A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed Images

2021-02-16 · Rui Li, Shunyi Zheng, Ce Zhang, Chenxi Duan 외

Semantic segmentation using fine-resolution remotely sensed images plays a critical role in many practical applications, such as urban planning, environmental protection, natural and anthropogenic landscape monitoring, e…

Decision Making Scene Understanding Segmentation Semantic Segmentation